[16025] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # KeyphraseExtractor - helper plugin to extract key phrases
|
---|
| 4 | #
|
---|
| 5 | # A component of the Greenstone digital library software
|
---|
| 6 | # from the New Zealand Digital Library Project at the
|
---|
| 7 | # University of Waikato, New Zealand.
|
---|
| 8 | #
|
---|
| 9 | # Copyright (C) 2008 New Zealand Digital Library Project
|
---|
| 10 | #
|
---|
| 11 | # This program is free software; you can redistribute it and/or modify
|
---|
| 12 | # it under the terms of the GNU General Public License as published by
|
---|
| 13 | # the Free Software Foundation; either version 2 of the License, or
|
---|
| 14 | # (at your option) any later version.
|
---|
| 15 | #
|
---|
| 16 | # This program is distributed in the hope that it will be useful,
|
---|
| 17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 19 | # GNU General Public License for more details.
|
---|
| 20 | #
|
---|
| 21 | # You should have received a copy of the GNU General Public License
|
---|
| 22 | # along with this program; if not, write to the Free Software
|
---|
| 23 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 24 | #
|
---|
| 25 | ###########################################################################
|
---|
| 26 |
|
---|
[15867] | 27 | package KeyphraseExtractor;
|
---|
| 28 |
|
---|
| 29 | use Kea;
|
---|
| 30 | use PrintInfo;
|
---|
[15887] | 31 | use strict;
|
---|
| 32 | no strict 'subs';
|
---|
[15867] | 33 |
|
---|
| 34 | BEGIN {
|
---|
| 35 | @KeyphraseExtractor::ISA = ('PrintInfo');
|
---|
| 36 | }
|
---|
| 37 |
|
---|
| 38 | my $arguments = [
|
---|
| 39 | { 'name' => "extract_keyphrases",
|
---|
| 40 | 'desc' => "{KeyphraseExtractor.extract_keyphrases}",
|
---|
| 41 | 'type' => "flag",
|
---|
| 42 | 'reqd' => "no" },
|
---|
| 43 | { 'name' => "extract_keyphrases_kea4",
|
---|
| 44 | 'desc' => "{KeyphraseExtractor.extract_keyphrases_kea4}",
|
---|
| 45 | 'type' => "flag",
|
---|
| 46 | 'reqd' => "no" },
|
---|
| 47 | { 'name' => "extract_keyphrase_options",
|
---|
| 48 | 'desc' => "{KeyphraseExtractor.extract_keyphrase_options}",
|
---|
| 49 | 'type' => "string",
|
---|
| 50 | 'deft' => "",
|
---|
| 51 | 'reqd' => "no" }
|
---|
| 52 | ];
|
---|
| 53 |
|
---|
| 54 | my $options = { 'name' => "KeyphraseExtractor",
|
---|
| 55 | 'desc' => "{KeyphraseExtractor.desc}",
|
---|
| 56 | 'abstract' => "yes",
|
---|
| 57 | 'inherits' => "yes",
|
---|
| 58 | 'args' => $arguments };
|
---|
| 59 |
|
---|
| 60 |
|
---|
| 61 | sub new {
|
---|
| 62 | my ($class) = shift (@_);
|
---|
| 63 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
| 64 | push(@$pluginlist, $class);
|
---|
| 65 |
|
---|
[15881] | 66 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 67 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
[15867] | 68 |
|
---|
[15881] | 69 | my $self = new PrintInfo($pluginlist, $inputargs, $hashArgOptLists, 1);
|
---|
[15867] | 70 |
|
---|
| 71 | return bless $self, $class;
|
---|
| 72 |
|
---|
| 73 | }
|
---|
| 74 | # extract metadata
|
---|
| 75 | sub extract_keyphrase_metadata {
|
---|
| 76 |
|
---|
| 77 | my $self = shift (@_);
|
---|
| 78 | my ($doc_obj) = @_;
|
---|
| 79 |
|
---|
| 80 | if ($self->{'extract_keyphrases'} || $self->{'extract_keyphrases_kea4'}) {
|
---|
| 81 | $self->extract_keyphrases($doc_obj);
|
---|
| 82 | }
|
---|
| 83 |
|
---|
| 84 | }
|
---|
| 85 |
|
---|
| 86 |
|
---|
| 87 | #adding kea keyphrases
|
---|
| 88 | sub extract_keyphrases
|
---|
| 89 | {
|
---|
| 90 | my $self = shift(@_);
|
---|
| 91 | my $doc_obj = shift(@_);
|
---|
| 92 |
|
---|
| 93 | # Use Kea 3.0 unless 4.0 has been specified
|
---|
| 94 | my $kea_version = "3.0";
|
---|
| 95 | if ($self->{'extract_keyphrases_kea4'}) {
|
---|
| 96 | $kea_version = "4.0";
|
---|
| 97 | }
|
---|
| 98 |
|
---|
| 99 | # Check that Kea exists, and tell the user where to get it if not
|
---|
| 100 | my $keahome = &Kea::get_Kea_directory($kea_version);
|
---|
| 101 | if (!-e $keahome) {
|
---|
| 102 | gsprintf(STDERR, "{KeyphraseExtractor.missing_kea}\n", $keahome, $kea_version);
|
---|
| 103 | return;
|
---|
| 104 | }
|
---|
| 105 |
|
---|
| 106 | my $thissection = $doc_obj->get_top_section();
|
---|
| 107 | my $text = "";
|
---|
| 108 | my $list;
|
---|
| 109 |
|
---|
| 110 | #loop through sections to gather whole doc
|
---|
| 111 | while (defined $thissection) {
|
---|
| 112 | my $sectiontext = $doc_obj->get_text($thissection);
|
---|
| 113 | $text = $text.$sectiontext;
|
---|
| 114 | $thissection = $doc_obj->get_next_section ($thissection);
|
---|
| 115 | }
|
---|
| 116 |
|
---|
| 117 | if($self->{'extract_keyphrase_options'}) { #if kea options flag is set, call Kea with specified options
|
---|
| 118 | $list = &Kea::extract_KeyPhrases ($kea_version, $text, $self->{'extract_keyphrase_options'});
|
---|
| 119 | } else { #otherwise call Kea with no options
|
---|
| 120 | $list = &Kea::extract_KeyPhrases ($kea_version, $text);
|
---|
| 121 | }
|
---|
| 122 |
|
---|
| 123 | if ($list){
|
---|
| 124 | # if a list of kea keyphrases was returned (ie not empty)
|
---|
| 125 | if ($self->{'verbosity'}) {
|
---|
| 126 | gsprintf(STDERR, "{KeyphraseExtractor.keyphrases}: $list\n");
|
---|
| 127 | }
|
---|
| 128 |
|
---|
| 129 | #add metadata to top section
|
---|
| 130 | $thissection = $doc_obj->get_top_section();
|
---|
| 131 |
|
---|
| 132 | # add all key phrases as one metadata
|
---|
| 133 | $doc_obj->add_metadata($thissection, "Keyphrases", $list);
|
---|
| 134 |
|
---|
| 135 | # add individual key phrases as multiple metadata
|
---|
| 136 | foreach my $keyphrase (split(',', $list)) {
|
---|
| 137 | $keyphrase =~ s/^\s+|\s+$//g;
|
---|
| 138 | $doc_obj->add_metadata($thissection, "Keyphrase", $keyphrase);
|
---|
| 139 | }
|
---|
| 140 | }
|
---|
| 141 | }
|
---|
| 142 |
|
---|
| 143 | 1;
|
---|